An Agentic Interface for End-to-End Probabilistic Seismic Hazard and Risk Analysis

Probabilistic seismic hazard and risk analyses are backbone to building codes, insurance pricing, and disaster management. Yet their open-engine pipelines remain accessible primarily to experts. We present the first agentic interface to the end-to-end probabilistic seismic hazard and risk chain via an open-source server, addressable through the Model Context Protocol (MCP). MCP wraps the OpenQuake engine and the 2020 European Seismic Hazard and Risk Models using twenty-four typed endpoints. Here, an agent is defined as a large language model (LLM) with tools. The LLM is confined to the role of an orchestrator so it plans, translates, and explains, while the OpenQuake engine and custom codes compute hazard values, damage probability, and loss. Each response carries source-model, ground-motion model (GMM), and certified data provenance for transparency. Results are benchmarked against ESHM20 at seventy-three cities; the replicated 475-year spectral accelerations match official values within a median of 5 %, and a full hazard-to-loss estimate runs in minutes. The interface additionally accepts a user-supplied empirical or machine-learning GMM on any tectonic region type of the published tree, and adds features that existing web services omit: conditional spectra, deterministic scenarios, surface hazard, per-building loss, retrofit comparison, and record selection with waveform retrieval. The proposed design layers transfer to other regional models, and to other hazards. Significance. An LLM-powered chatbot accesses the full European probabilistic seismic hazard and risk models (ESHM20 and ESRM20). It reproduces the published reference at a median 5 % ln-unit level across multiple cities. Users can provide custom ground-motion models and run the regional logic tree with them in a single conversational session, chaining from hazard through to economic loss. The agent provides additional features beyond those the ESHM20/ESRM20 developers intended.